Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to standard features or specifications in descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    standard or default configurations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    contentLoaded
    -0.65
    MessageOf
    -0.65
     protoimpl
    -0.58
    AddTagHelper
    -0.58
     فريبيس
    -0.57
    IUrlHelper
    -0.57
     виправивши
    -0.56
    SuppressLint
    -0.55
    endphp
    -0.54
    omock
    -0.54
    POSITIVE LOGITS
     Habit
    0.39
     CURIAM
    0.38
     standard
    0.36
     Quartz
    0.36
    Habit
    0.35
    cens
    0.35
     getDefault
    0.35
     natu
    0.34
    ByDefault
    0.34
     starter
    0.33
    Act Density 0.015%

    No Known Activations